Surrogate for nonlinear time series analysis

We present a surrogate for use in nonlinear time series analysis. This surrogate algorithm has significant advantages over the most commonly used surrogates, in that it provides a more robust statistical test by producing an entire population of surrogates that are consistent with the null hypothesis. We will show that for the currently used surrogate algorithms, although individual surrogate files are consistent with the null hypothesis the population of surrogates generated is not. The surrogate is tested on a linear stochastic process and a continuous nonlinear system.